ICRA 2021, one of the most influential international conference on robotics and automation,was held in Xi'an, China from May 31 to June 5. Associate Professor Daolin Ma from Department of Engineering Mechanics won this year’s highest honor for the conference -- Best Conference Paper Award. 

ICRA (International Conference on Robotics and Automation), hosted by IEEE (Institute of Electrical and Electronics Engineers), is an annual academic conference covering advances in robotics. It is one of the premier conferences in its field, as many of the most important innovations in robotics or automation were first presented on it. ICRA Best Conference Paper Award recognizes the best paper presented at the IEEE International Conference on Robotics and Automation. 

Among the 4,056 submissions from 59 countries/regions, 4 paper entered the finalist and only one paper was selected as the Best Conference Paper. Professor Ma's paper “Extrinsic Contact Sensing with Relative-Motion Tracking from Distributed Tactile Measurements” won the award. 

Below is the comment from the Awarding Committee: 

“The paper makes a notable contribution to the important and re-emerging field of tactile perception by solving the problem of contact localization between an unknown object held by an imprecise grasp and the unknown environment with which it is in contact. This paper represents an excellent theory-to-practice exercise as the novel proposal of using extrinsic tactile array data to infer contact is verified with a new tactile sensor and real robotic manipulation in a simplified, but realistic environment.The authors also provide a robust and honest discussion of results, both positive and negative, for reader evaluation.”

As introduced by Prof. Daolin Ma, knowing how to utilize the sense of touch from the fingertips, in the scenarios of human executing insertion or assembly tasks, is a challenging open problem. This paper finds that key to the precise perception and control capabilities are the ability of motion tracking with the sense of touch.  Prof. Ma achieved accurate motion tracking for the grasped object via tactile sensing without knowing geometry of the object and without placing markers on the object, whose accuracy is close to VICON, the most accurate commercial motion tracking system which needs to add markers. 

Based on the capability of motion tracking, this paper further proposed the theoretical framework of “Extrinsic Contact Sensing”, which realized the localization of external contact between object and the environment with tactile when the robot is performing contact-rich manipulation tasks, such as autonomous assembly. This capability provides key state estimation for the long-expected tactile-servo-control and paves the road for precise contact control of intelligent robots. At the same time, since traditional research on tactile sensing focuses heavily on force sensing, this paper promotes the value of tactile perception in the novel dimension of accurate motion tracking, which leads a new direction for tactile sensor development and optimization. 

Daolin Ma is currently an associate professor in the Department of Engineering Mechanics in NAOCE, and his lab focuses on frontier research in tactile perception and control for robotic manipulation. He is also recipient of the Champion of Amazon Robotics Challenge (2017) stow Task, winner of Amazon Robotics Best System Paper Award (2018).